Cs640 introduction to computer networks
This presentation is the property of its rightful owner.
Sponsored Links
1 / 20

CS640: Introduction to Computer Networks PowerPoint PPT Presentation

  • Uploaded on
  • Presentation posted in: General

CS640: Introduction to Computer Networks. Aditya Akella Lecture 20 - Queuing and Basics of QoS. Queuing Disciplines. Each router must implement some queuing discipline Scheduling discipline Drop policy Queuing allocates both bandwidth and buffer space:

Download Presentation

CS640: Introduction to Computer Networks

An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.

- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -

Presentation Transcript

Cs640 introduction to computer networks

CS640: Introduction to Computer Networks

Aditya Akella

Lecture 20 -

Queuing and Basics of QoS

Queuing disciplines

Queuing Disciplines

  • Each router must implement some queuing discipline

    • Scheduling discipline

    • Drop policy

  • Queuing allocates both bandwidth and buffer space:

    • Bandwidth: which packet to serve (transmit) next

    • Buffer space: which packet to drop next (when required)

  • Queuing also affects latency

Typical internet queuing

Typical Internet Queuing

  • FIFO + drop-tail

    • Simplest choice

    • Used widely in the Internet

    • FIFO: scheduling discipline

    • Drop-tail: drop policy

  • FIFO (first-in-first-out)

    • Implies single class of traffic, no priority

  • Drop-tail

    • Arriving packets get dropped when queue is full regardless of flow or importance

Fifo drop tail problems

FIFO + Drop-tail Problems

  • Lock-out problem

    • Allows a few flows to monopolize the queue space

    • Send more, get more  No implicit policing

  • Full queues

    • TCP detects congestion from loss

    • Forces network to have long standing queues in steady-state

    • Queueing delays – bad for time sensitive traffic

    • Synchronization: end hosts react to same events

      • Full queue  empty  Full  empty…

  • Poor support for bursty traffic

Lock out problem

Lock-out Problem

  • Priority queueing can solve some problems

    • Starvation

    • Determining priorities is hard

  • Simpler techniques: Random drop

    • Packet arriving when queue is full causes some random packet to be dropped

  • Drop front

    • On full queue, drop packet at head of queue

  • Random drop and drop front solve the lock-out problem but not the full-queues problem

Random early detection red

Random Early Detection (RED)

  • Drop packets before queue becomes full (early drop)

  • Detect incipient congestion

  • Avoid window synchronization

    • Randomly mark packets

  • Random drop helps avoid bias against bursty traffic

Red algorithm

RED Algorithm

  • Maintain running average of queue length

  • If avg < minth do nothing

    • Low queuing, send packets through

  • If avg > maxth, drop packet

    • Protection from misbehaving sources

  • Else mark packet in a manner proportional to queue length

    • Notify sources of incipient congestion

Red operation

RED Operation

Min thresh

Max thresh

Average Queue Length






Avg queue length

Fair queuing goals

Fair Queuing: Goals

  • How do you protect the most important packets?

    • How do you provide some isolation in general?

    • Simple priority queuing does not help

  • Two approaches:

    • Fair Queuing (in itself is sufficient)

    • Leaky bucket (with other techniques which we will cover next class)

  • FQ key goal: Allocate resources “fairly”

    • Keep separate queue for each flow

  • Isolate ill-behaved users

  • Still achieve statistical muxing

    • One flow can fill entire pipe if no contenders

    • Work conserving scheduler never idles link if it has a packet

What is fairness

What is “Fairness”?

  • At what granularity?

    • Flows, connections, domains?

  • What if users have different RTTs/links/etc.

    • TCP is “RTT-Fair”

      • BW inversely proportional to RTT of flow

    • Should they share a link equally or be TCP-fair?

  • Maximize fairness index?

    • Fairness = (Sxi)2/n(Sxi2) 0<fairness<1

Max min fairness

Max-min Fairness

  • Allocate user with “small” demand what it wants, evenly divide unused resources to “big” users

  • Formally:

    • Resources allocated in terms of increasing demand

    • No source gets resource share larger than its demand

    • Sources with unsatisfied demands get equal share of resource

Implementing max min fairness

Implementing Max-min Fairness

  • Use separate queues per flow

    • Round-robin scheduling across queues

  • Why not simple round robin at packet level?

    • Variable packet length  can get more service by sending bigger packets

  • Ideally: Bitwise round robin among all queues

Bit by bit rr illustration

Bit-by-bit RR Illustration

  • Not feasible to interleave bits on real networks

    • FQ simulates bit-by-bit RR

Bit by bit rr simulation

Bit-by-bit RR Simulation

  • Single flow: clock ticks when a bit is transmitted. For packet i:

    • Pi = length, Ai = arrival time, Si = begin transmit time, Fi = finish transmit time

    • Fi = Si+Pi = max (Fi-1, Ai) + Pi

  • Multiple flows: clock ticks when a bit from all active flows is transmitted  round number

    • Can calculate Fi for each packet if number of flows is know at all times

      • Why do we need to know flow count?  need to know A  This can be complicated

Fair queuing

Fair Queuing

  • Mapping bit-by-bit schedule onto packet transmission schedule

  • Transmit packet with the lowest Fi at any given time

Fq illustration

FQ Illustration

Flow 1

Flow 2



Flow n

Variation: Weighted Fair Queuing (WFQ)  Flows can have weightKey to QoS, as we will see in next class.

No pre emption


Flow 1


Flow 2





No Pre-emption

Flow 1

Flow 2




Cannot preempt packet

currently being transmitted

Fair queuing tradeoffs

Fair Queuing Tradeoffs

  • FQ can control congestion by monitoring flows

    • Need flows to be adaptive to avoid congestion collapse

  • Complex state

    • Must keep queue per flow

      • Hard in routers with many flows (e.g., backbone routers)

      • Flow aggregation is a possibility (e.g. do fairness per domain)

  • Complex computation

    • Classification into flows may be hard

    • Must keep queues sorted by finish times

    • Must track number of flows at fine time scales

Token bucket for traffic policing at the network edge

Token Bucket for Traffic Policing at the Network Edge


Tokens enter bucket at rate r



Bucket depth b: capacity of bucket


Enough tokens 

packet goes through,

tokens removed



Not enough tokens  wait for tokens to accumulate

Token bucket characteristics

Token Bucket Characteristics

  • On the long run, rate is limited to r

  • On the short run, a burst of size b can be sent

  • Amount of traffic entering at interval T is bounded by:

    • Traffic = b + r*T

    • Can provide a lose sense of isolation among flows.

      • Especially because the send rate of each flow is throttled at the source

      • Still need some mechanism within the network to ensure performance guarantees

  • Login